|国家预印本平台
首页|Adversarial Agent Behavior Learning in Autonomous Driving Using Deep Reinforcement Learning

Adversarial Agent Behavior Learning in Autonomous Driving Using Deep Reinforcement Learning

Adversarial Agent Behavior Learning in Autonomous Driving Using Deep Reinforcement Learning

来源:Arxiv_logoArxiv
英文摘要

Existing approaches in reinforcement learning train an agent to learn desired optimal behavior in an environment with rule based surrounding agents. In safety critical applications such as autonomous driving it is crucial that the rule based agents are modelled properly. Several behavior modelling strategies and IDM models are used currently to model the surrounding agents. We present a learning based method to derive the adversarial behavior for the rule based agents to cause failure scenarios. We evaluate our adversarial agent against all the rule based agents and show the decrease in cumulative reward.

Arjun Srinivasan、Anubhav Paras、Aniket Bera

自动化基础理论计算技术、计算机技术

Arjun Srinivasan,Anubhav Paras,Aniket Bera.Adversarial Agent Behavior Learning in Autonomous Driving Using Deep Reinforcement Learning[EB/OL].(2025-08-21)[2025-09-02].https://arxiv.org/abs/2508.15207.点此复制

评论